Program synthesis or code generation aims to generate a program that satisfies a problem
specification. Recent approaches using large-scale pretrained language models (LMs) have …

Programming is a powerful and ubiquitous problem-solving tool. Systems that can assist
programmers or even generate programs themselves could make programming more …

Code intelligence leverages machine learning techniques to extract knowledge from
extensive code corpora, with the aim of developing intelligent tools to improve the quality …

Code completion, which aims to predict the following code token (s) according to the code
context, can improve the productivity of software development. Recent work has proved that …

Powered by recent advances in code-generating models, AI assistants like Github Copilot
promise to change the face of programming forever. But what is this new face of …

A proper code evaluation metric (CEM) profoundly impacts the evolution of code generation,
which is an important research field in NLP and software engineering. Prevailing match …

Code generation aims to automatically generate source code from high-level task
specifications, which can significantly increase productivity of software engineering …

Large Language Models (LLMs) have demonstrated remarkable performance in code
completion. However, due to the lack of domain-specific knowledge, they may not be optimal …

Software testing is a crucial aspect of software development, and the creation of high-quality
tests that adhere to best practices is essential for effective maintenance. Recently, Large …

Automated software debugging is a crucial task for improving the productivity of software
developers. Many neural-based techniques have been proven effective for debugging …